Adaptive sliding Mode Control for Nonholonomic Mobile Robots based on Neural Networks

To improve the tracking precision of mobile robots with unknown disturbances, an adaptive sliding mode control method with stronger robustness is proposed based on the neural networks. A new control law is designed, in which the equivalent term is replaced by a double power term to improve the convergence rate of sliding mode control. Moreover, the RBF neural network is employed to estimate the upper bound of the uncertainties and to compensate for the unknown parameters and nonparametric disturbances. The precision of trajectory tracking control is improved. This control algorithm is simple and more applicable to mobile robots. The stability is proved, and the simulations demonstrate the superiority and feasibility of the proposed algorithm.